Move custom GPU atomics into separate namespace. Add a script to print the include path.
- Move the custom
atomicMin/Max/Mul
functions to namespacepystencils::runtime::gpu
, such that no name conflicts may ever arise with native CUDA/HIP functions- Other than CUDA, HIP defines
atomicMin
,atomicMax
for floating-point types, so our definitions were raising duplicate-definition errors
- Other than CUDA, HIP defines
- Use C++17 in cupy JIT compiler (for qualified namespace names)
- Make the
pystencils.include
module executable as a script to print the path to the pystencils header directory to stdout
Edited by Frederik Hennig
Merge request reports
Activity
Please register or sign in to reply